mlsanityData to 14 Oct 2026

SAMRI: Segment Any MRI

arXiv 2510.26635 ↗First posted 30 Oct 2025eess.IV cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

Summary: SAMRI is an MRI-specialized adaptation of the Segment Anything Model achieving superior whole-body MRI segmentation, particularly for small and clinically critical structures, through box and point prompts for rapid annotation. Purpose: Existing SAM adaptations treat MRI as a generic modality, overlooking variable tissue contrast, intensity inhomogeneity, and clinically important small structures. We propose an MRI-specialized foundation model with strong whole-body segmentation and zero-shot generalization for direct use on any MRI annotation task. Methods: SAMRI fine-tunes only the mask decoder of SAM (ViT-B/16), keeping encoders frozen to preserve pretrained representations and eliminate redundant passes-reducing training time by 94%, trainable parameters by 96%, and FLOPs by ~99% versus full-model retraining. Training used 1.1 million 2D slice-mask pairs from 30 datasets spanning 47 targets, T1/T2/FLAIR/DWI contrasts, and whole-body anatomy, with focal-Dice loss and bounding-box (with optional point) prompts. Sizes were stratified by mask area (small: <0.5%; medium: 0.5-3.5%; large: >3.5%), and significance assessed by the Wilcoxon signed-rank test. Results: SAMRI with box+point prompts achieved mean DSC 0.87 +/- 0.11 across 47 targets, outperforming MedSAM (0.74 +/- 0.24) by 17.6% (p < 0.05), with largest gains for small (+42.4%) and medium (+26.9%) structures. On six zero-shot datasets, SAMRI achieved mean DSC 0.85, outperforming baselines. Inference requires only ~4.5 GB VRAM through an interactive interface on standard hardware. Conclusion: Decoder-only fine-tuning on a large, MRI-specific corpus delivers superior whole-body segmentation with strong zero-shot generalization, particularly for small and clinically salient structures. Public code, pretrained models, and an interactive interface make SAMRI deployable for MRI segmentation research and clinical workflows.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 31 of its 75 references that are in the map. First posted on arXiv 30 Oct 2025.

Builds on

31 of 75 references.

References · 31

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2023Segment Anythingcited by 8,234
  3. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,292
  4. 20163D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotationcited by 1,476
  5. 2018Attention U-Net: Learning Where to Look for the Pancreascited by 1,435
  6. 2021The Medical Segmentation Decathloncited by 628
  7. 2017Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentationscited by 620
  8. 2018Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challengecited by 511
  9. 2023Medical SAM Adapter: Adapting Segment Anything Model for Medical Image Segmentationcited by 490
  10. 2019A large annotated medical image dataset for the development and evaluation of segmentation algorithmscited by 373
  11. 2022AMOS: A Large-Scale Abdominal Multi-Organ Benchmark for Versatile Medical Image Segmentationcited by 351
  12. 2020CHAOS Challenge -- Combined (CT-MR) Healthy Abdominal Organ Segmentationcited by 309
19 more
  1. 2018nnU-Net: Self-adapting Framework for U-Net-Based Medical Image Segmentationcited by 291
  2. 2023Segment Anything Model for Medical Image Analysis: an Experimental Studycited by 291
  3. 2022Medical Image Segmentation Review: The success of U-Netcited by 191
  4. 2019Standardized Assessment of Automatic Segmentation of White Matter Hyperintensities and Results of the WMH Segmentation Challengecited by 115
  5. 2022ISLES 2022: A multi-center magnetic resonance imaging stroke lesion segmentation datasetcited by 106
  6. 2023MA-SAM: Modality-agnostic SAM Adaptation for 3D Medical Image Segmentationcited by 82
  7. 2024TotalSegmentator MRI: Robust Sequence-independent Segmentation of Multiple Anatomic Structures in MRIcited by 59
  8. 2022CrossMoDA 2021 challenge: Benchmark of Cross-Modality Domain Adaptation techniques for Vestibular Schwannoma and Cochlea Segmentationcited by 58
  9. 2023Segment Anything Model for Medical Images?cited by 39
  10. 2021End-to-end Prostate Cancer Detection in bpMRI via 3D CNNs: Effects of Attention Mechanisms, Clinical Priori and Decoupled False Positive Reductioncited by 32
  11. 2024Foundation Models for Biomedical Image Segmentation: A Surveycited by 28
  12. 2018MDU-Net: Multi-scale Densely Connected U-Net for biomedical image segmentationcited by 27
  13. 2023DeSAM: Decoupled Segment Anything Model for Generalizable Medical Image Segmentationcited by 26
  14. 2023From CNN to Transformer: A Review of Medical Image Segmentation Modelscited by 22
  15. 2022Visual Semantic Segmentation Based on Few/Zero-Shot Learning: An Overviewcited by 16
  16. 2024Segment Anything Model Can Not Segment Anything: Assessing AI Foundation Model's Generalizability in Permafrost Mappingcited by 9
  17. 2021CAN3D: Fast 3D Medical Image Segmentation via Compact Context Aggregationcited by 7
  18. 2024MCP-MedSAM: A Powerful Lightweight Medical Segment Anything Model Trained with a Single GPU in Just One Daycited by 4
  19. 2024Architecture Analysis and Benchmarking of 3D U-shaped Deep Learning Models for Thoracic Anatomical Segmentationcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026SAMRI-3D: Adapting SAM2 for 3D MRI Segmentation with Global Volume Tokenscited by 0
  2. 2026A4-MR: Abnormality-aware Anatomical Alignment for MRcited by 0